© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25988
    Prev
    Next
    INDEX
    Explanations

    a little bit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bit
    -0.17
    bit
    -0.14
     bits
    -0.13
     Bit
    -0.13
    BIT
    -0.12
    -bit
    -0.12
    Bit
    -0.12
     somewhat
    -0.10
    anson
    -0.10
    hog
    -0.10
    POSITIVE LOGITS
     ago
    0.13
    ially
    0.10
    umen
    0.10
    edly
    0.10
    allen
    0.10
     of
    0.09
    anan
    0.09
    ewing
    0.09
    ingly
    0.09
    ë§Į
    0.08
    Activations Density 0.018%

    No Known Activations